{"total":2360,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962,"area":null},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"area":null},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"area":null},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101,"area":null},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058,"area":null},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806,"area":null},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751,"area":null},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712,"area":null},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691,"area":null},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565,"area":null},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527,"area":null},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525,"area":null},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524,"area":null},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522,"area":null},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"area":null},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417,"area":null},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396,"area":null},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379,"area":null},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377,"area":null},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368,"area":null},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310,"area":null},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"area":null},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293,"area":null},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289,"area":null},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288,"area":null},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288,"area":null},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281,"area":null},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260,"area":null},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224,"area":null},{"id":"2103.04098","title":"WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition","created":"2021-03-06","cited_by_count":223,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216,"area":null},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198,"area":null},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189,"area":null},{"id":"2303.13899","title":"Robust Test-Time Adaptation in Dynamic Scenarios","created":"2023-03-24","cited_by_count":189,"area":null},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188,"area":null},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"area":null},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186,"area":null},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"area":null},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169,"area":null},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2303.02190","title":"MixVPR: Feature Mixing for Visual Place Recognition","created":"2023-03-03","cited_by_count":161,"area":null},{"id":"2303.14535","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","created":"2023-03-25","cited_by_count":160,"area":null},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"area":null},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156,"area":null},{"id":"2204.05088","title":"M$^2$BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation","created":"2022-04-11","cited_by_count":156,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154,"area":null},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2207.09052","title":"Balanced Contrastive Learning for Long-Tailed Visual Recognition","created":"2022-07-19","cited_by_count":144,"area":null},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"area":null},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137,"area":null},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137,"area":null},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137,"area":null},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"area":null},{"id":"2112.00463","title":"The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization","created":"2021-12-01","cited_by_count":131,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2106.01883","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","created":"2021-06-03","cited_by_count":130,"area":null}],"next_cursor":"100"}